# Joint Learning of Word and Label Embeddings for Sequence Labelling in Spoken Language Understanding

arXiv: https://arxiv.org/abs/1910.07150 · HTML: https://mlsanity.com/paper/1910.07150/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2019.

## Built on by (most cited first, 1 of 1)

- [Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models](https://mlsanity.com/paper/2108.08451/) (2021)

## Abstract (arXiv)

We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association from the training data. Compared to the state-of-the-art methods, our approach does not require label embeddings as part of the input and therefore lends itself nicely to a wide range of model architectures. In addition, our architecture computes contextual distances between words and labels to avoid adding contextual windows, thus reducing memory footprint. We validate the approach on established spoken dialogue datasets and show that it can achieve state-of-the-art performance with much fewer trainable parameters.